Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
It tackles document understanding for applications like financial analysis and scientific discovery, but as a survey, it is incremental in summarizing existing advances rather than introducing new methods.
This survey addresses the problem of document understanding by proposing Multimodal Retrieval-Augmented Generation (RAG) to overcome limitations in existing methods, such as loss of structural detail and context modeling issues, and provides a systematic review including a taxonomy, datasets, benchmarks, and open challenges.
Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key limitations: the former loses structural detail, while the latter struggles with context modeling. Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, i.e., combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG. This approach enables holistic retrieval and reasoning across all modalities, unlocking comprehensive document intelligence. Recognizing its importance, this paper presents a systematic survey of Multimodal RAG for document understanding. We propose a taxonomy based on domain, retrieval modality, and granularity, and review advances involving graph structures and agentic frameworks. We also summarize key datasets, benchmarks, and applications, and highlight open challenges in efficiency, fine-grained representation, and robustness, providing a roadmap for future progress in document AI.